Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    first, digits, math

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     definiert
    0.65
     coworker
    0.63
     பெயர்
    0.62
     objectForKey
    0.61
     ditentukan
    0.61
    सूची
    0.61
     portátil
    0.60
    ብ
    0.60
     belieb
    0.59
     conceit
    0.59
    POSITIVE LOGITS
    三个
    0.77
     첫
    0.73
     первые
    0.72
    まずは
    0.72
    两位
    0.67
     Patient
    0.67
     first
    0.66
     पहली
    0.66
    Patient
    0.66
     अंकों
    0.64
    Act Density 0.341%

    No Known Activations